AiCostCompare

Compare models

Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.

Claude Opus 4.5GPT-5.6 Sol
Claude Opus 4.5

Anthropic

GPT-5.6 Sol

OpenAI

Pricing
Input $/1M$5.00$5.00
Output $/1M$25.00$30.00
Blended $/1M (3:1)$10.00$11.25
Cache read $/1M$0.50$0.50
Cache write $/1M$6.25$6.25
Quality indices
Intelligence Index34.758.9
Coding Index77.4
Math Index62.7
Agentic Index54
Speed & latency
Output speed (tok/s)6867
Time to first token1.30s120.38s
Time to first answer token1.30s120.38s
Benchmarks (Artificial Analysis)
MMLU-Pro88.9%
GPQA Diamond81.0%94.1%
Humanity's Last Exam12.9%47.2%
LiveCodeBench73.8%
SciCode47.0%56.1%
AIME 202562.7%
IFBench43.0%72.7%
AA-LCR (Long Context Reasoning)65.3%73.7%
Terminal-Bench Hard40.9%65.9%
Terminal-Bench 2.188.0%
τ²-Bench (Telecom)86.3%85.1%
τ³-Bench Banking33.0%
Design Arena (Elo)
Website1,274
Web apps1,216
Full-stack1,215
Mobile apps1,254
Android native1,169
UI components1,280
Data viz1,278
SVG1,227
3D1,272
Game dev1,288
Code categories1,276
ASCII art1,231
Specs
Context window200K1.05M
Max output tokens64K128K
Input modalitiesfile, image, textfile, image, text
TokenizerClaudeGPT